Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14164
    Prev
    Next
    INDEX
    Explanations

    occurrences of asynchronous programming terms, particularly related to `await` and `async`

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -0.66
    1
    -0.62
    3
    -0.62
     ddelweddau
    -0.60
    The
    -0.59
    2
    -0.58
    s
    -0.54
    ca
    -0.53
    d
    -0.53
    B
    -0.51
    POSITIVE LOGITS
    tagHelperRunner
    1.11
     CreateTagHelper
    1.04
    ValueStyle
    0.88
     Promise
    0.85
    antMatchers
    0.80
    LEncoder
    0.76
    arakhand
    0.76
     ainfi
    0.75
    LEGGI
    0.75
     Vikipedi
    0.73
    Activations Density 0.020%

    No Known Activations